AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs Paper • 2508.16153 • Published 8 days ago • 107
CRISP: Persistent Concept Unlearning via Sparse Autoencoders Paper • 2508.13650 • Published 11 days ago • 14
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification Paper • 2508.05629 • Published 23 days ago • 166
view article Article Tiny Agents in Python: a MCP-powered agent in ~70 lines of code By celinah and 3 others • May 23 • 158